config.json

{
  "_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelsw6weqh39r8vdmibp",
  "architectures": [
    "TraVisionForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_travisionlm.TraVisionLMConfig",
    "AutoModelForCausalLM": "modeling_travisionlm.TraVisionForCausalLM"
  },
  "hidden_size": 1280,
  "ignore_index": -100,
  "image_token_index": 50257,
  "model_type": "travisionlm",
  "num_image_tokens": 256,
  "projection_dim": 768,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "lm_head"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "text_config": {
    "architectures": [
      "GPT2LMHeadModel"
    ],
    "bos_token_id": 0,
    "eos_token_id": 0,
    "model_type": "gpt2",
    "n_ctx": 1024,
    "n_embd": 1280,
    "n_head": 20,
    "n_layer": 36,
    "pad_token_id": 0,
    "reorder_and_upcast_attn": true,
    "scale_attn_by_inverse_layer_idx": true,
    "task_specific_params": {
      "text-generation": {
        "do_sample": true,
        "max_length": 50
      }
    },
    "torch_dtype": "float32",
    "vocab_size": 51282
  },
  "torch_dtype": "float16",
  "transformers_version": "4.42.4",
  "vision_config": {
    "image_size": 256,
    "model_type": "siglip_vision_model",
    "projection_dim": 768
  }
}